Search

In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level framework that augments the classification network to adapt to catastrophic distribution shifts during training, enabling the network to achieve a stable consolidation of all seen tasks. However, the CBA module adjusts distribution shifts in a class-specific manner, exacerbating the stability gap issue and, to some extent, fails to meet the need for continual testing in online CL. To mitigate this challenge, we further propose a novel class-agnostic CBA module that separately aggregates the posterior probabilities of classes from new and old tasks, and applies a stable adjustment to the resulting posterior probabilities. We combine the two kinds of CBA modules into a unified Dual-CBA module, which thus is capable of adapting to catastrophic distribution shifts and simultaneously meets the real-time testing requirements of online CL. Besides, we propose Incremental Batch Normalization (IBN), a tailored BN module to re-estimate its population statistics for alleviating the feature bias arising from the inner loop optimization problem of our bi-level framework. To validate the effectiveness of the proposed method, we theoretically provide some insights into how it mitigates catastrophic distribution shifts, and empirically demonstrate its superiority through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.

Quantizing large language models (LLMs) presents significant challenges, primarily due to outlier activations that compromise the efficiency of low-bit representation. Traditional approaches mainly focus on solving Normal Outliers-activations with consistently high magnitudes across all tokens. However, these techniques falter when dealing with Massive Outliers, which are significantly higher in value and often cause substantial performance losses during low-bit quantization. In this study, we propose DuQuant, an innovative quantization strategy employing rotation and permutation transformations to more effectively eliminate both types of outliers. Initially, DuQuant constructs rotation matrices informed by specific outlier dimensions, redistributing these outliers across adjacent channels within different rotation blocks. Subsequently, a zigzag permutation is applied to ensure a balanced distribution of outliers among blocks, minimizing block-wise variance. An additional rotation further enhances the smoothness of the activation landscape, thereby improving model performance. DuQuant streamlines the quantization process and demonstrates superior outlier management, achieving top-tier results in multiple tasks with various LLM architectures even under 4-bit weight-activation quantization. Our code is available at https://github.com/Hsu1023/DuQuant., Comment: 26 pages, 13 figures

Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. The significant challenges for deep learning-based image fusion algorithms are the lack of a definitive ground truth as well as the corresponding distance measurement, with current manually given loss functions constrain the flexibility of model and generalizability for unified fusion tasks. To overcome these limitations, we introduce a unified image fusion framework based on meta-learning, named ReFusion, which provides a learning paradigm that obtains the optimal fusion loss for various fusion tasks based on reconstructing the source images. Compared to existing methods, ReFusion employs a parameterized loss function, dynamically adjusted by the training framework according to the specific scenario and task. ReFusion is constituted by three components: a fusion module, a loss proposal module, and a source reconstruction module. To ensure the fusion module maximally preserves the information from the source images, enabling the reconstruction of the source images from the fused image, we adopt a meta-learning strategy to train the loss proposal module using reconstruction loss. The update of the fusion module relies on the fusion loss proposed by the loss proposal module. The alternating updates of the three modules mutually facilitate each other, aiming to propose an appropriate fusion loss for different tasks and yield satisfactory fusion results. Extensive experiments demonstrate that ReFusion is capable of adapting to various tasks, including infrared-visible, medical, multi-focus, and multi-exposure image fusion. The code will be released.

Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily forgets the previously learned knowledge and biases toward the newly received task. To address this problem, we propose a Continual Bias Adaptor (CBA) module to augment the classifier network to adapt to catastrophic distribution change during training, such that the classifier network is able to learn a stable consolidation of previously learned tasks. In the testing stage, CBA can be removed which introduces no additional computation cost and memory overhead. We theoretically reveal the reason why the proposed method can effectively alleviate catastrophic distribution shifts, and empirically demonstrate its effectiveness through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks., Comment: Accepted by ICCV 2023

Exposure to bio-aerosols such as mold spores and pollen can lead to adverse health effects. There is a need for a portable and cost-effective device for long-term monitoring and quantification of various bio-aerosols. To address this need, we present a mobile and cost-effective label-free bio-aerosol sensor that takes holographic images of flowing particulate matter concentrated by a virtual impactor, which selectively slows down and guides particles larger than ~6 microns to fly through an imaging window. The flowing particles are illuminated by a pulsed laser diode, casting their inline holograms on a CMOS image sensor in a lens-free mobile imaging device. The illumination contains three short pulses with a negligible shift of the flowing particle within one pulse, and triplicate holograms of the same particle are recorded at a single frame before it exits the imaging field-of-view, revealing different perspectives of each particle. The particles within the virtual impactor are localized through a differential detection scheme, and a deep neural network classifies the aerosol type in a label-free manner, based on the acquired holographic images. We demonstrated the success of this mobile bio-aerosol detector with a virtual impactor using different types of pollen (i.e., bermuda, elm, oak, pine, sycamore, and wheat) and achieved a blind classification accuracy of 92.91%. This mobile and cost-effective device weighs ~700 g and can be used for label-free sensing and quantification of various bio-aerosols over extended periods since it is based on a cartridge-free virtual impactor that does not capture or immobilize particulate matter., Comment: 23 Pages, 5 Figures, 1 Table

Pseudo-labeling has proven to be a promising semi-supervised learning (SSL) paradigm. Existing pseudo-labeling methods commonly assume that the class distributions of training data are balanced. However, such an assumption is far from realistic scenarios and thus severely limits the performance of current pseudo-labeling methods under the context of class-imbalance. To alleviate this problem, we design a bias adaptive classifier that targets the imbalanced SSL setups. The core idea is to automatically assimilate the training bias caused by class imbalance via the bias adaptive classifier, which is composed of a novel bias attractor and the original linear classifier. The bias attractor is designed as a light-weight residual network and optimized through a bi-level learning framework. Such a learning strategy enables the bias adaptive classifier to fit imbalanced training data, while the linear classifier can provide unbiased label prediction for each class. We conduct extensive experiments under various imbalanced semi-supervised setups, and the results demonstrate that our method can be applied to different pseudo-labeling models and is superior to current state-of-the-art methods., Comment: Accepted by ICLR 2023

The success of meta-learning on existing benchmarks is predicated on the assumption that the distribution of meta-training tasks covers meta-testing tasks. Frequent violation of the assumption in applications with either insufficient tasks or a very narrow meta-training task distribution leads to memorization or learner overfitting. Recent solutions have pursued augmentation of meta-training tasks, while it is still an open question to generate both correct and sufficiently imaginary tasks. In this paper, we seek an approach that up-samples meta-training tasks from the task representation via a task up-sampling network. Besides, the resulting approach named Adversarial Task Up-sampling (ATU) suffices to generate tasks that can maximally contribute to the latest meta-learner by maximizing an adversarial loss. On few-shot sine regression and image classification datasets, we empirically validate the marked improvement of ATU over state-of-the-art task augmentation strategies in the meta-testing performance and also the quality of up-sampled tasks.

Various volatile aerosols have been associated with adverse health effects; however, characterization of these aerosols is challenging due to their dynamic nature. Here we present a method that directly measures the volatility of particulate matter (PM) using computational microscopy and deep learning. This method was applied to aerosols generated by electronic cigarettes (e-cigs), which vaporize a liquid mixture (e-liquid) that mainly consists of propylene glycol (PG), vegetable glycerin (VG), nicotine, and flavoring compounds. E-cig generated aerosols were recorded by a field-portable computational microscope, using an impaction-based air sampler. A lensless digital holographic microscope inside this mobile device continuously records the inline holograms of the collected particles. A deep learning-based algorithm is used to automatically reconstruct the microscopic images of e-cig generated particles from their holograms, and rapidly quantify their volatility. To evaluate the effects of e-liquid composition on aerosol dynamics, we measured the volatility of the particles generated by flavorless, nicotine-free e-liquids with various PG/VG volumetric ratios, revealing a negative correlation between the particles' volatility and the volumetric ratio of VG in the e-liquid. For a given PG/VG composition, the addition of nicotine dominated the evaporation dynamics of the e-cig aerosol and the aforementioned negative correlation was no longer observed. We also revealed that flavoring additives in e-liquids significantly decrease the volatility of e-cig aerosol. The presented holographic volatility measurement technique and the associated mobile device might provide new insights on the volatility of e-cig generated particles and can be applied to characterize various volatile PM., Comment: 23 Pages, 4 Figures

We present a virtual image refocusing method over an extended depth of field (DOF) enabled by cascaded neural networks and a double-helix point-spread function (DH-PSF). This network model, referred to as W-Net, is composed of two cascaded generator and discriminator network pairs. The first generator network learns to virtually refocus an input image onto a user-defined plane, while the second generator learns to perform a cross-modality image transformation, improving the lateral resolution of the output image. Using this W-Net model with DH-PSF engineering, we extend the DOF of a fluorescence microscope by ~20-fold. This approach can be applied to develop deep learning-enabled image reconstruction methods for localization microscopy techniques that utilize engineered PSFs to improve their imaging performance, including spatial resolution and volumetric imaging throughput., Comment: 7 Pages, 3 Figures, 1 Table

Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a method to identity suspected noisy labels and then correct them. Current approaches to correcting corrupted labels usually need certain pre-defined label correction rules or manually preset hyper-parameters. These fixed settings make it hard to apply in practice since the accurate label correction usually related with the concrete problem, training data and the temporal information hidden in dynamic iterations of training process. To address this issue, we propose a meta-learning model which could estimate soft labels through meta-gradient descent step under the guidance of noise-free meta data. By viewing the label correction procedure as a meta-process and using a meta-learner to automatically correct labels, we could adaptively obtain rectified soft labels iteratively according to current training problems without manually preset hyper-parameters. Besides, our method is model-agnostic and we can combine it with any other existing model with ease. Comprehensive experiments substantiate the superiority of our method in both synthetic and real-world problems with noisy labels compared with current SOTA label correction strategies., Comment: 12 pages,6 figures

To alleviate the adverse effect of rain streaks in image processing tasks, CNN-based single image rain removal methods have been recently proposed. However, the performance of these deep learning methods largely relies on the covering range of rain shapes contained in the pre-collected training rainy-clean image pairs. This makes them easily trapped into the overfitting-to-the-training-samples issue and cannot finely generalize to practical rainy images with complex and diverse rain streaks. Against this generalization issue, this study proposes a new network architecture by enforcing the output residual of the network possess intrinsic rain structures. Such a structural residual setting guarantees the rain layer extracted by the network finely comply with the prior knowledge of general rain streaks, and thus regulates sound rain shapes capable of being well extracted from rainy images in both training and predicting stages. Such a general regularization function naturally leads to both its better training accuracy and testing generalization capability even for those non-seen rain configurations. Such superiority is comprehensively substantiated by experiments implemented on synthetic and real datasets both visually and quantitatively as compared with current state-of-the-art methods.

Rain streaks might severely degenerate the performance of video/image processing tasks. The investigations on rain removal from video or a single image has thus been attracting much research attention in the field of computer vision and pattern recognition, and various methods have been proposed against this task in the recent years. However, there is still not a comprehensive survey paper to summarize current rain removal methods and fairly compare their generalization performance, and especially, still not a off-the-shelf toolkit to accumulate recent representative methods for easy performance comparison and capability evaluation. Aiming at this meaningful task, in this study we present a comprehensive review for current rain removal methods for video and a single image. Specifically, these methods are categorized into model-driven and data-driven approaches, and more elaborate branches of each approach are further introduced. Intrinsic capabilities, especially generalization, of representative state-of-the-art methods of each approach have been evaluated and analyzed by experiments implemented on synthetic and real data both visually and quantitatively. Furthermore, we release a comprehensive repository, including direct links to 74 rain removal papers, source codes of 9 methods for video rain removal and 20 ones for single image rain removal, 19 related project pages, 6 synthetic datasets and 4 real ones, and 4 commonly used image quality metrics, to facilitate reproduction and performance comparison of current existing methods for general users. Some limitations and research issues worthy to be further investigated have also been discussed for future research of this direction.

We report a framework based on a generative adversarial network (GAN) that performs high-fidelity color image reconstruction using a single hologram of a sample that is illuminated simultaneously by light at three different wavelengths. The trained network learns to eliminate missing-phase-related artifacts, and generates an accurate color transformation for the reconstructed image. Our framework is experimentally demonstrated using lung and prostate tissue sections that are labeled with different histological stains. This framework is envisaged to be applicable to point-of-care histopathology, and presents a significant improvement in the throughput of coherent microscopy systems given that only a single hologram of the specimen is required for accurate color imaging., Comment: 25 pages, 8 Figures, 2 Tables

Three-dimensional (3D) fluorescence microscopy in general requires axial scanning to capture images of a sample at different planes. Here we demonstrate that a deep convolutional neural network can be trained to virtually refocus a 2D fluorescence image onto user-defined 3D surfaces within the sample volume. With this data-driven computational microscopy framework, we imaged the neuron activity of a Caenorhabditis elegans worm in 3D using a time-sequence of fluorescence images acquired at a single focal plane, digitally increasing the depth-of-field of the microscope by 20-fold without any axial scanning, additional hardware, or a trade-off of imaging resolution or speed. Furthermore, we demonstrate that this learning-based approach can correct for sample drift, tilt, and other image aberrations, all digitally performed after the acquisition of a single fluorescence image. This unique framework also cross-connects different imaging modalities to each other, enabling 3D refocusing of a single wide-field fluorescence image to match confocal microscopy images acquired at different sample planes. This deep learning-based 3D image refocusing method might be transformative for imaging and tracking of 3D biological samples, especially over extended periods of time, mitigating photo-toxicity, sample drift, aberration and defocusing related challenges associated with standard 3D fluorescence microscopy techniques., Comment: 47 pages, 5 figures (main text)

We report resolution enhancement in scanning electron microscopy (SEM) images using a generative adversarial network. We demonstrate the veracity of this deep learning-based super-resolution technique by inferring unresolved features in low-resolution SEM images and comparing them with the accurately co-registered high-resolution SEM images of the same samples. Through spatial frequency analysis, we also report that our method generates images with frequency spectra matching higher resolution SEM images of the same fields-of-view. By using this technique, higher resolution SEM images can be taken faster, while also reducing both electron charging and damage to the samples., Comment: 8 pages, 4 figures

Deep learning brings bright-field microscopy contrast to holographic images of a sample volume, bridging the volumetric imaging capability of holography with the speckle- and artifact-free image contrast of bright-field incoherent microscopy., Comment: 3 pages

Aggregation-based assays, using micro- and nano-particles have been widely accepted as an efficient and cost-effective bio-sensing tool, particularly in microbiology, where particle clustering events are used as a metric to infer the presence of a specific target analyte and quantify its concentration. Here, we present a sensitive and automated readout method for aggregation-based assays using a wide-field lens-free on-chip microscope, with the ability to rapidly analyze and quantify microscopic particle aggregation events in 3D, using deep learning-based holographic image reconstruction. In this method, the computation time for hologram reconstruction and particle autofocusing steps remains constant, regardless of the number of particles/clusters within the 3D sample volume, which provides a major throughput advantage, brought by deep learning-based image reconstruction. As a proof of concept, we demonstrate rapid detection of herpes simplex virus (HSV) by monitoring the clustering of antibody-coated micro-particles, achieving a detection limit of ~5 viral copies per micro-liter (i.e., ~25 copies per test)., Comment: 15 pages, 5 figures